© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206350
    Prev
    Next
    INDEX
    Explanations

    project related phrase

    np_acts-logits-general · gemini-2.5-flash-lite

    decades of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venues
    0.49
    ของผู้
    0.48
     խ
    0.48
    änden
    0.48
     لیکن
    0.47
    và
    0.46
    eningrad
    0.45
    และการ
    0.45
     αλλά
    0.45
    archi
    0.45
    POSITIVE LOGITS
    Hue
    0.46
     உதய
    0.44
     reigned
    0.43
     resembled
    0.43
     fasted
    0.42
    疑似
    0.42
    ్రియ
    0.42
    里
    0.42
     আহম্মদ
    0.42
    laug
    0.42
    Activations Density 0.002%

    No Known Activations